Multi-sensors data fusion system for wireless sensors networks of factory monitoring via BPN technology

This study attempts to apply a back-propagation network (BPN) for multi-sensors data fusion in a wireless sensor networks (WSNs) system with a node-sink mobile network structure. This investigate is to finish the factory monitoring at environment monitoring services (EMS). These practice wireless sensor network circuits include temperature, humidity, ultraviolet, and illumination four variable measurement components. These data fields of each sensor nodes contain the properties and specifications of that signal process rules, the remote engineers can manage the multi-sensors data fusion using the browser, and the WSNs system then classification the data fusion database via the Internet and mobile network. Moreover, The BPN training approach is significant that improves data fusion system in accuracy and classification with parallel computing for data fusion efficiency. The final phase of the classification fusion system applies parallel BPN technology to process data fusion, and can solve the problem of various signals states. This study is considered implemented on the Yang-Fen Automation Electrical Engineering Company as a case study. The experiment is continued for six months, and engineers are also used to operating the web-based classification fusion system. Therefore, the cooperative plan described above is analyzed and discussed here. Finally, these papers propose the tradition methods compare with the innovative BPN methods. 2009 Elsevier Ltd. All rights reserved.